English(EN) GeoTopoDiff: Learning Geometry--Topology Graph Priors through Boundary-Constrained Mixed Diffusion for Sparse-Slice 3D Porous Reconstruction

GeoTopoDiff框架从稀疏CT切片重建三维多孔微结构

作者 PulseAugur 编辑部 · [2 个来源] · 2026-05-05 13:53

研究人员开发了GeoTopoDiff，一个新颖的基于图扩散的框架，旨在从稀疏CT切片重建三维多孔微结构。该方法将扩散先验学习从体素空间转移到混合图状态空间，从而能够同时对孔隙几何和拓扑进行建模。在PTFE和Fontainebleau砂岩上的实验表明，形态和传输误差显著降低，表明在稀疏观测下后验不确定性有所改善。 AI

影响引入了一种从稀疏数据进行三维重建的新方法，可能改进材料科学和工程领域的模拟。

排序理由这是一篇详细介绍新的三维重建框架的研究论文。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CV TIER_1 English(EN) · Yue Shi, Peng Wang, Mingzhe Yu, Yunlong Zhao, Li Liu, Gareth D Hatton, Yan Lyu, Liangxiu Han · 2026-05-06 04:00

GeoTopoDiff: Learning Geometry--Topology Graph Priors through Boundary-Constrained Mixed Diffusion for Sparse-Slice 3D Porous Reconstruction

arXiv:2605.03764v1 Announce Type: new Abstract: Diffusion-based voxel prior modelling is challenging for the reconstruction of large-scale 3D porous microstructures. Due to the demanding requirements for simultaneously modelling both the continuous pore morphology and the discret…
arXiv cs.CV TIER_1 English(EN) · Liangxiu Han · 2026-05-05 13:53

GeoTopoDiff: Learning Geometry--Topology Graph Priors through Boundary-Constrained Mixed Diffusion for Sparse-Slice 3D Porous Reconstruction

Diffusion-based voxel prior modelling is challenging for the reconstruction of large-scale 3D porous microstructures. Due to the demanding requirements for simultaneously modelling both the continuous pore morphology and the discrete pore-throat topology, the diffusion models req…

报道来源 [2]

GeoTopoDiff: Learning Geometry--Topology Graph Priors through Boundary-Constrained Mixed Diffusion for Sparse-Slice 3D Porous Reconstruction

GeoTopoDiff: Learning Geometry--Topology Graph Priors through Boundary-Constrained Mixed Diffusion for Sparse-Slice 3D Porous Reconstruction

相关实体

相关话题